def completeTest(self, treelikerArgs, processes=1):
self.generateExamplesUnified()
bestClassifiers = []
terms = self.termsByDepth(
) # This sorting is needed later in bnet learning
treeliker = TreeLikerWrapper(self, *treelikerArgs)
def processTerm(term):
return term, treeliker.runTermTest(term)
nets = defaultdict(dict)
allresults = tuple(parallel_map_dill(processes, processTerm, terms))
combis = set()
for term, learned in allresults:
for clfName, i in learned:
combis.add((term, clfName))
#for clf, X_train, y_train, X_test, y_test, X_validation, y_validation, g_train, g_test, g_validation in folds:
if clfName in nets[i]:
net = nets[i][clfName]
else:
net = BayesNet(i, clfName, self)
nets[i][clfName] = net
net.generateCPD(
term
) #, clf, X_train, y_train, X_test, y_test, X_validation, y_validation, g_train, g_test, g_validation)
for i, byClf in sorted(nets.items()):
for clfName, net in byClf.items():
net.bake()
net.predict()
debug("Generating plots.")
#for term, learned in allresults:
# for clfName, folds in learned.items():
plt.figure(figsize=(6, 12))
for term, clfName in combis:
plt.clf()
termN = self[term]['name']
cvdir = getTermPath(termN)
#folds2 = [(nets[i][clfName].nodeAsClf(term),)+f[1:] for i,f in enumerate(folds)]
s1 = plt.subplot(211, adjustable='box', aspect=1)
s1.axis('equal')
#s1.legend(loc='center left', bbox_to_anchor=(1, 0.5))
plotRoc(termN, clfName, termN)
s2 = plt.subplot(212, adjustable='box', aspect=1)
s2.axis('equal')
#s2.legend(loc='center left', bbox_to_anchor=(1, 0.5))
plotRoc(termN,
clfName,
"Bayes correction",
clfs=(nets[i][clfName].nodeAsClf(term)
for i in range(NUM_FOLDS)))
#plotRoc("Bayes correction", folds2)
print(str(cvdir / (clfName.replace(" ", "_") + '_roc.png')))
plt.savefig(str(cvdir / (clfName.replace(" ", "_") + '_roc.png')))
plt.savefig(str(cvdir / (clfName.replace(" ", "_") + '_roc.ps')))
debug("Finished complete test.")
def completeTest(self, treelikerArgs, processes = 1):
self.generateExamplesUnified()
bestClassifiers = []
terms = self.termsByDepth() # This sorting is needed later in bnet learning
treeliker = TreeLikerWrapper(self, *treelikerArgs)
def processTerm(term):
return term, treeliker.runTermTest(term)
nets = defaultdict(dict)
allresults = tuple(parallel_map_dill(processes, processTerm, terms))
combis = set()
for term, learned in allresults:
for clfName, i in learned:
combis.add((term,clfName))
#for clf, X_train, y_train, X_test, y_test, X_validation, y_validation, g_train, g_test, g_validation in folds:
if clfName in nets[i]:
net = nets[i][clfName]
else:
net = BayesNet(i, clfName, self)
nets[i][clfName] = net
net.generateCPD(term)#, clf, X_train, y_train, X_test, y_test, X_validation, y_validation, g_train, g_test, g_validation)
for i, byClf in sorted(nets.items()):
for clfName, net in byClf.items():
net.bake()
net.predict()
debug("Generating plots.")
#for term, learned in allresults:
# for clfName, folds in learned.items():
plt.figure(figsize = (6,12))
for term,clfName in combis:
plt.clf()
termN = self[term]['name']
cvdir = getTermPath(termN)
#folds2 = [(nets[i][clfName].nodeAsClf(term),)+f[1:] for i,f in enumerate(folds)]
s1 = plt.subplot(211, adjustable='box', aspect=1)
s1.axis('equal')
#s1.legend(loc='center left', bbox_to_anchor=(1, 0.5))
plotRoc(termN, clfName, termN)
s2 = plt.subplot(212, adjustable='box', aspect=1)
s2.axis('equal')
#s2.legend(loc='center left', bbox_to_anchor=(1, 0.5))
plotRoc(termN, clfName, "Bayes correction",
clfs = (nets[i][clfName].nodeAsClf(term) for i in range(NUM_FOLDS) ))
#plotRoc("Bayes correction", folds2)
print(str(cvdir/(clfName.replace(" ","_")+'_roc.png')))
plt.savefig(str(cvdir/(clfName.replace(" ","_")+'_roc.png')))
plt.savefig(str(cvdir/(clfName.replace(" ","_")+'_roc.ps')))
debug("Finished complete test.")
def runTermTest(self, term):
term = self.ontology[term]['name']
debug("Preparing for TreeLiker on term %s." % term)
resultPath = getTermPath(term)
batchPath = resultPath / 'batch.treeliker'
datasetPath = resultPath / 'dataset.txt'
batchFile = "set(algorithm, relf_grounding_counting)\n" \
"set(verbosity, %d)\n" \
"set(output_type, train_test)\n" \
"set(examples, '%s')\n" \
"set(template, [%s])\n" \
"set(use_sampling, true)\n" \
"set(num_samples, %d)\n" \
"set(sample_size, %d)\n" \
"set(covered_class, '%s')\n\n" % (
dp.utils.verbosity,
datasetPath.name,
self.template,
self.samples,
self.sample_size,
term)
with datasetPath.open() as ds:
dataSetLen = len([*ds]) # Counts lines
for i, (train, test) in enumerate(
cross_validation.KFold(dataSetLen, NUM_FOLDS)):
path = resultPath / str(i)
if not path.is_dir():
path.mkdir()
batchFile += "set(output, '%s')\n" \
"set(train_set, [%s])\n" \
"set(test_set, [%s])\n" \
"work(yes)\n" % (
path.name,
",".join(map(str,train)),
",".join(map(str,test)))
with batchPath.open('w') as bf:
bf.write(batchFile)
self._runTreeLiker(resultPath, batchPath)
return learningTest(resultPath)
def runTermTest(self, term):
term = self.ontology[term]['name']
debug("Preparing for TreeLiker on term %s." % term)
resultPath = getTermPath(term)
batchPath = resultPath / 'batch.treeliker'
datasetPath = resultPath / 'dataset.txt'
batchFile = "set(algorithm, relf_grounding_counting)\n" \
"set(verbosity, %d)\n" \
"set(output_type, train_test)\n" \
"set(examples, '%s')\n" \
"set(template, [%s])\n" \
"set(use_sampling, true)\n" \
"set(num_samples, %d)\n" \
"set(sample_size, %d)\n" \
"set(covered_class, '%s')\n\n" % (
dp.utils.verbosity,
datasetPath.name,
self.template,
self.samples,
self.sample_size,
term)
with datasetPath.open() as ds:
dataSetLen = len([*ds]) # Counts lines
for i, (train, test) in enumerate(cross_validation.KFold(dataSetLen, NUM_FOLDS)):
path = resultPath / str(i)
if not path.is_dir():
path.mkdir()
batchFile += "set(output, '%s')\n" \
"set(train_set, [%s])\n" \
"set(test_set, [%s])\n" \
"work(yes)\n" % (
path.name,
",".join(map(str,train)),
",".join(map(str,test)))
with batchPath.open('w') as bf:
bf.write(batchFile)
self._runTreeLiker(resultPath, batchPath)
return learningTest(resultPath)
def generateExamplesUnified(self):
#return
debug("Generating unified datasets.")
terms = self.termsByDepth(False)
#rootname = self.ontology[self.root]['name']
with ExitStack() as stack: # Closes all files when exited
files = [(term, stack.enter_context((getTermPath(term) / 'dataset.txt').open('w')))
for term
in (self[t]['name'] for t in self.ontology.keys())
]#if term != rootname]
#for i, geneName in enumerate(self.genes):
for geneName in self.genes:
#debug("%d. Writing gene %s." % (i, geneName))
gene = self.geneFactory.getGene(geneName)
repg = ", ".join(gene.logicalRepresentation())
for term, output in files:
if geneName not in self.associations[term]:
term = '~'+term
e = '"%s" %s' % (term, repg)
print(e, file=output)
def generateExamplesUnified(self):
#return
debug("Generating unified datasets.")
terms = self.termsByDepth(False)
#rootname = self.ontology[self.root]['name']
with ExitStack() as stack: # Closes all files when exited
files = [
(term,
stack.enter_context(
(getTermPath(term) / 'dataset.txt').open('w')))
for term in (self[t]['name'] for t in self.ontology.keys())
] #if term != rootname]
#for i, geneName in enumerate(self.genes):
for geneName in self.genes:
#debug("%d. Writing gene %s." % (i, geneName))
gene = self.geneFactory.getGene(geneName)
repg = ", ".join(gene.logicalRepresentation())
for term, output in files:
if geneName not in self.associations[term]:
term = '~' + term
e = '"%s" %s' % (term, repg)
print(e, file=output)
